Models to Predict Naturalness of Images Including Skin Colours

Tian, Dalin; Peng, Rui; Chang, Chung Pai; Luo, Ming Ronnier

doi:10.1007/978-981-16-0503-1_5

Cited by 3 publications

(4 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…According to the literature, there have been studies where the naturalness was involved in 2D images [2,4,8,9,[11][12][13][14][15][16]28], 3D images [17,29], and 2D prints [3,5,10]. Naturalness as an attribute was mentioned in Kadyrova et al's [1] work on attributes for the quality assessment of 2.5D prints.…”

Section: Discussionmentioning

confidence: 99%

“…Naturalness along with details were found to be the most important/salient perceptual attributes that describe perceptual differences of 2D images [12]. There are also works dedicated to model naturalness of 2D images [13][14][15][16]. For instance, Choi et al [13] used the sharpness and colorfulness of images, shadow-detail reproduction, and lack of washed-out appearance factors along with memory colors for 2D image naturalness modeling.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Effect of Elevation and Surface Roughness on Naturalness Perception of 2.5D Decor Prints

2022

View full text Add to dashboard Cite

Naturalness is a complex concept. It can involve a variety of attributes. In this work, we considered the effect of elevation and surface roughness on naturalness perception of 2.5D decor prints for four material categories. We found that elevation has an impact on the naturalness perception of 2.5D decor prints and that it is linked with content. The observers found lower elevation to be more natural for wood and glass 2.5D prints while there was no clear tendency for stone and metal 2.5D prints. We also found the perceptual attributes used for naturalness assessment of 2.5D decor prints. The top five ones are color, roughness, gloss, elevation, and lightness. The obtained findings can be useful for companies that produce 2.5D prints.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Effect of Elevation and Surface Roughness on Naturalness Perception of 2.5D Decor Prints

2022

View full text Add to dashboard Cite

show abstract

“…The correlation coefficients R show that the skin colors models are not as accurate as other models (R = 0.68 for image quality and R = 0.76 for naturalness) because, in our previous study [8], the model of skin colors can be further sorted by the skin types including Chinese, Caucasian, and African, etc. The ten original images selected in this study consist of many different skin colors, so it is reasonable that this model could not accurately predict every image.…”

Section: Comparison Tablementioning

confidence: 88%

Models to predict naturalness and image quality for images containing three memory colors: sky, grass, and skin

Jason¹,

Tian²,

Luo³

2021

cic

Self Cite

View full text Add to dashboard Cite

When evaluating the image quality, people mostly would like to concentrate on the color appearance of memory objects, representing the naturalness and reality of the image scene. Generally, an image with objects which have perfect memory colors reproduction will give natural and harmonious feelings. Many previous studies had proved the critical role of naturalness in image quality assessment, but it was still tough to scale the image naturalness precisely. In this study, natural images with blue sky, green grass, and skin colors were selected and partially rendered to develop the model of preference and naturalness of typical memory colors. A psychophysical experiment was conducted to collect the visual data of these images. Afterward, the psychophysical data were used to build the preference models and naturalness models, respectively. The models were then compared with previous studies. Results showed that the new models could accurately predict the preference and naturalness of target memory colors.

show abstract

“…She then developed an image quality model consisting of these two image attributes for natural scenes. Our previous study 8 evaluated the visual performance of peak brightness, blackness, colorfulness, contrast, reality, texture details, and sharpness of High Dynamic Range (HDR) images on an Organic Light Emitting‐Diode (OLED) display. Results showed that image reality played a vital role in image color property.…”

Section: Introductionmentioning

confidence: 99%

Image naturalness model based on prototypical memory colors (sky, grass, and skin)

Tian

Luo

2022

Color Research & Application

Self Cite

View full text Add to dashboard Cite

Image naturalness is a potent attribute to enhance image quality, and it is related to people's perception of memory colors. Many previous experiments aimed to locate the memory colors on different media. Their findings indicate that the memory colors obtained vary between color patches and images and between experimental techniques. However, there were no satisfying models with appropriate memory color centers to scale the image naturalness. This study generated an image database including three prototypical memory colors images (sky, grass, and skin) and their local processed images. First, visual naturalness and preference data were collected from a psychophysical experiment. Then, the distribution of naturalness followed by memory color positions was analyzed. Based on the distribution pattern, the ellipsoid models for each prototypical memory color were established. The results from the present memory color centers were compared with those from the other studies. Results show that the present color centers always give better prediction accuracy in image naturalness models. Finally, an image preference model was developed based on the image naturalness and colorfulness.

show abstract

Models to Predict Naturalness of Images Including Skin Colours

Cited by 3 publications

References 5 publications

Effect of Elevation and Surface Roughness on Naturalness Perception of 2.5D Decor Prints

Effect of Elevation and Surface Roughness on Naturalness Perception of 2.5D Decor Prints

Models to predict naturalness and image quality for images containing three memory colors: sky, grass, and skin

Image naturalness model based on prototypical memory colors (sky, grass, and skin)

Contact Info

Product

Resources

About